데이터 공부를 기록하는 공간

import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns import warnings warnings.filterwarnings('ignore') df = pd.read_csv('./Mall_Customers/Mall_Customers.csv') print(df.shape) df.head(3) df = df.rename(columns = {"Annual Income (k$)": "income", "Spending Score (1-100)":"score", "Gender":"gender", "Age":"age"}) sns.pairplot(df, hue='gender') df.drop('Custome..

1. 데이터 전처리 import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns df = pd.read_csv("./mobile_cust_churn/mobile_cust_churn.csv") df.drop(columns=['Unnamed: 0','id'], axis=1, inplace=True) target = 'CHURN' features = df.columns.tolist()[:-1] numeric_features = df.select_dtypes(include=['int64']).columns.tolist() category_features= [] for col in features: if co..

1. library import import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns plt.style.use('seaborn-whitegrid') from datetime import datetime import statsmodels.api as sm from statsmodels.graphics.tsaplots import plot_acf, plot_pacf from statsmodels.tsa.arima_model import ARIMA from statsmodels.tsa.statespace.sarimax import SARIMAX from matplotlib.pyplot import ..

import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns import warnings warnings.filterwarnings('ignore') train = pd.read_csv('./titanic/train.csv') test = pd.read_csv('./titanic/test.csv') 1. 데이터 전처리 # check null data train.isnull().sum() test.isnull().sum() # category, numeric feature seperation target = 'Survived' train[target].value_counts() features = tr..